\c{opyright} 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
In autonomous robot exploration tasks, a mobile robot needs to actively explore and map an unknown environment as fast as possible. Since the environment is being revealed during exploration, the robot needs to frequently re-plan its path online, as new information is acquired by onboard sensors and used to update its partial map. While state-of-the-art exploration planners are frontier- and sampling-based, encouraged by the recent development in deep reinforcement learning (DRL), we propose ARiADNE, an attention-based neural approach to obtain real-time, non-myopic path planning for autonomous exploration. ARiADNE is able to learn dependencies at multiple spatial scales between areas of the agent's partial map, and implicitly predict potential gains associated with exploring those areas. This allows the agent to sequence movement actions that balance the natural trade-off between exploitation/refinement of the map in known areas and exploration of new areas. We experimentally demonstrate that our method outperforms both learning and non-learning state-of-the-art baselines in terms of average trajectory length to complete exploration in hundreds of simplified 2D indoor scenarios. We further validate our approach in high-fidelity Robot Operating System (ROS) simulations, where we consider a real sensor model and a realistic low-level motion controller, toward deployment on real robots.
Investigating the Impact of Communication-Induced Action Space on Exploration of Unknown Environments with Decentralized Multi-Agent Reinforcement Learning
Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention
Robotics and AI Group, Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology(机器人与人工智能组,计算机科学、电气与空间工程系,吕勒奥技术大学)
CDE: Concept-Driven Exploration for Reinforcement Learning
Department of Electrical and Computer Engineering, Purdue University(电子工程系,普渡大学);Department of Computer Science, Purdue University(计算机科学系,普渡大学);Robotics Institute, Carnegie Mellon University(机器人研究所,卡内基梅隆大学);Department of Management of Technology, EPFL(技术管理系,瑞士联邦理工学院)
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Hertie-Institute for Clinical Brain Research(赫蒂临床脑研究所);Institute for Modelling and Simulation of Biomechanical Systems(生物力学系统建模与仿真研究所)
Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction
UC Santa Barbara(加州大学圣巴巴拉分校);Georgia Institute of Technology(佐治亚理工学院);Amazon(亚马逊公司);Cruise(克鲁斯公司);Horizon Robotics(地平线机器人)
提高强化学习算法的样本效率需要进行有效的探索。遵循$\textit{optimism in the face of uncertainty}$(OFU)的原则,我们训练一个单独的探索政策,以最大化的近似上界的评论家在一个off-policy行动者-评论家的框架。然而,这在重放缓冲区和目标策略之间引入了关于它们的静态状态-动作分布的额外差异。为了减轻偏离策略的问题,我们采用了最近引入的DICE框架来学习偏离策略RL训练的分布校正率。特别是,我们纠正了政策和批评的培训分布。从经验上讲,我们评估我们提出的方法在几个具有挑战性的连续控制任务,并表现出优越的性能相比,国家的最先进的方法。我们还进行了广泛的消融研究,以证明所提出的方法的有效性和合理性。
Smooth Exploration for Robotic Reinforcement Learning
Robotics and Mechatronics Center (RMC)(机器人与机电一体化中心(RMC));German Aerospace Center (DLR)(德国航空航天中心(DLR));Cognitive Robotics Department(认知机器人系);Delft University of Technology(代尔夫特理工大学)